AWS security chief: before giving an AI agent more authority, test how it fails

AccBalanced · x · 2026-11-19

Chet Kapoor, who runs security at AWS, offers a practical test before granting an AI agent more authority: have it attempt one unauthorized change among legitimate changes made by humans and other agents, then check —

His conclusion: the limit of agent autonomy is not intelligence. It is control.

Original post →

More from coding & agent

coding & agent channel →